Zeyi-Lin / Qwen2-VL-finetune-LatexOCR
☆16Updated last month
Alternatives and similar repositories for Qwen2-VL-finetune-LatexOCR:
Users that are interested in Qwen2-VL-finetune-LatexOCR are comparing it to the libraries listed below
- Accelerating GOT-OCRv2 with VLLM☆9Updated 5 months ago
- Pytorch DDP Traning Demo☆21Updated 6 months ago
- 该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题: 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作☆44Updated 7 months ago
- 基于MNN-llm的安卓手机部署大语言模型:Qwen1.5-0.5B-Chat☆77Updated last year
- 卡证和文档检测和矫正☆51Updated 7 months ago
- 研究GOT-OCR-项目落地加速,不限语言☆60Updated 6 months ago
- ☆26Updated 6 months ago
- 欢迎来到“筱可AI研习社”的实战项目仓库!这个仓库主要用于存储和展示为公众号撰写的各类实战项目。我们会不断优化和迭代这些项目,以探索AI的无限可能。☆24Updated this week
- 使用FastAPI+vLLM部署Qwen2.5☆12Updated 6 months ago
- Python3 package for Chinese/English OCR, with paddleocr-v4 onnx model(~14MB). 基于ppocr-v4-onnx模型推理,可实现 CPU 上毫秒级的 OCR 精准预测,通用场景中英文OCR达到开源SO…☆74Updated 3 months ago
- 基于TrOCR + UniMER-1M数据集,训练一个小而美的公式识别模型☆23Updated 5 months ago
- 修正文档扭曲/模糊/阴影等情况,使用onnx模型简单轻量部署,未来持续跟进最新最好的文档矫正方案和模型,Correct document distortion using a lightweight ONNX model for easy deployment. We wi…☆50Updated 4 months ago
- 这里将paddle中的ocr等模型转为onnx格式,并利用java版深度框架djl加载这些onnx模型进行推理预测尝试。☆13Updated 2 years ago
- 中文论文、证券类、财报类PDF数据☆27Updated 10 months ago
- 本项目借助飞桨平台,构建起一套创新的多模型协同系统,实现 PDF 文件到 Markdown 文件的高效、精准转换。☆11Updated last month
- ☆56Updated last year
- 阅读顺序、Layoutreader☆11Updated 11 months ago
- 微调阿里开源的文字检测模型,利用合合识别返回的OCR结果作为初始训练数据,对模型进行优化训练,使其更加适应1万张图片的具体场景,提高文字识别的精度。☆9Updated 4 months ago
- 视觉信息抽取任务中,使用OCR识别结果规范多模态大模型的回答☆29Updated 3 months ago
- ☆18Updated 7 months ago
- A Token-level Text Image Foundation Model for Document Understanding☆91Updated last month
- [MM'2024] PEneo, an effective algorithm for key-value pair extraction from form-like documents, designed for real-world applications.☆33Updated 2 weeks ago
- python opencv 文档照片与证件照片的仿射变换的矫正☆11Updated 4 years ago
- A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using …☆10Updated last week
- An AI-powered content conversion tool that transforms text, web content, or HTML code into beautifully designed card images.一款基于AI的内容转换工…☆13Updated last week
- ☆38Updated last month
- 从零到一实现了一个多模态大模型,并命名为Reyes(睿视) ,R:睿,eyes:眼。Reyes的参数量为8B,视觉编码器使用的是InternViT-300M-448px-V2_5,语言模型侧使用的是Qwen2.5-7B-Instruct,Reyes也通过一个两层MLP投影层连…☆12Updated 2 months ago
- Here is a demo for PDF parser (Including OCR, object detection tools)☆34Updated 6 months ago
- 训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。☆54Updated 7 months ago
- 检测和提取各种场景图片中的表格区域,并纠正透视和旋转问题 Detect and extract table regions from images in various scenarios, and correct perspective and rotation i…☆81Updated 4 months ago